© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8410
    Prev
    Next
    INDEX
    Explanations

    words related to being and wanting, especially "to be."

    oai_token-act-pair · gemini-2.0-flash

    Relationships/Mating

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.59
     disambiguazione
    -0.58
    RenderAtEndOf
    -0.57
     Bourgoin
    -0.55
    mappedBy
    -0.54
    AndEndTag
    -0.52
    tvguidetime
    -0.51
     jupe
    -0.50
    InputTagHelper
    -0.50
    riwal
    -0.49
    POSITIVE LOGITS
    stdc
    0.60
    falls
    0.55
     Theo
    0.49
    
    0.48
    fromnode
    0.48
     PHPUnit
    0.48
     wo
    0.48
    Kaynakça
    0.48
     defaultstate
    0.47
    comb
    0.47
    Activations Density 8.497%

    No Known Activations